CN110082424B - Multi-scale abnormal region recommendation system and method for rapid pipeline magnetic flux leakage data - Google Patents
Multi-scale abnormal region recommendation system and method for rapid pipeline magnetic flux leakage data Download PDFInfo
- Publication number
- CN110082424B CN110082424B CN201910387892.8A CN201910387892A CN110082424B CN 110082424 B CN110082424 B CN 110082424B CN 201910387892 A CN201910387892 A CN 201910387892A CN 110082424 B CN110082424 B CN 110082424B
- Authority
- CN
- China
- Prior art keywords
- abnormal
- window
- scale
- windows
- estimation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 131
- 230000004907 flux Effects 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000002093 peripheral effect Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 5
- 230000007547 defect Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000007405 data analysis Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003305 oil spill Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000003902 seawater pollution Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/72—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
- G01N27/82—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
- G01N27/83—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws by investigating stray magnetic fields
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Electrochemistry (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
The invention provides a system and a method for rapidly recommending a multi-scale abnormal region of pipeline magnetic flux leakage data, and relates to the technical field of pipeline detection. The inventionThe method comprises the following steps: step 1: acquiring a magnetic leakage signal of a section of pipeline, dividing a multi-scale window body, and extracting abnormal edges of N scale levels to obtain an abnormal window body set; step 2: carrying out abnormal region estimation on the abnormal window body set to obtain an abnormal estimation set; and 3, step 3: the boundary is accurate; according to the abnormal estimation set, W k All the windows in the set carry out area ratio of adjacent windows, traverse the abnormal estimation set W', remove the windows with the area ratio smaller than lambda, and select the outermost periphery window in the overlapped windows in the current set as the abnormal recommendation area; the method can find the abnormity with larger size and obvious signal, can find the smaller abnormity at the same time, and can provide sufficient abnormity candidate area; the method has obvious rapidity and is particularly suitable for huge data sets of pipelines.
Description
Technical Field
The invention relates to the technical field of pipeline detection, in particular to a system and a method for rapidly recommending a multi-scale abnormal region of pipeline magnetic flux leakage data.
Background
Pipeline transportation is called five transportation modes together with railways, highways, waterways and aviation by virtue of the characteristics of high efficiency, safety and reliability. Along with the increase of pipeline time in service, because of pipeline material problem, outer damage and the influence of medium corrosion, the pipeline situation worsens gradually, has latent damage and leaks the risk. Once leakage occurs, not only can air pollution be caused, but also severe explosion can be easily caused. In 2011, an oil spill accident occurs in a Bohai Bay, 385 cubic meters of crude oil leaked in the accident are counted according to the national sea bureau, and 5500 square kilometers of sea water pollution is caused. Therefore, in order to ensure energy transportation and ecological safety, the pipelines must be regularly subjected to security inspection and maintenance.
Non-destructive testing (NDT) is widely used as an important tool for maintaining pipeline safety. Among them, magnetic flux leakage detection is widely applied to nearly 90% of in-service pipelines as a nondestructive detection method. A complete magnetic leakage data analysis process includes 5 parts, namely: data preprocessing, abnormal region recommendation, abnormal identification, defect size reverse estimation and defect safety evaluation. The data preprocessing part completes filtering of base value correction of original data; an abnormal region recommending section obtains a position of the abnormal region; the abnormity identification part completes classification identification of abnormal positions, such as defects, valves, instruments and the like; the defect size estimating part realizes the mapping of defect signals to sizes, and the defect safety evaluating part calculates the safety level of the defects and determines whether maintenance is needed.
Abnormal region recommendations are a key and challenging problem in the magnetic flux leakage data analysis flow. A good abnormal region recommendation algorithm not only has position accuracy and edge accuracy, but also has a rapid capability. In practical application, recommendation for abnormal regions is based on a traditional exhaustive search algorithm, influence of a candidate region sampling problem on algorithm efficiency is not considered, and huge search space finally wastes a large amount of time. Meanwhile, due to the influence of noise, the detection omission is easy to occur due to small abnormity.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a system and a method for rapidly recommending the pipeline magnetic flux leakage data multi-scale abnormal region aiming at the defects of the prior art.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
on one hand, the invention provides a multi-scale abnormal region recommendation system for rapid pipeline magnetic flux leakage data, which comprises an input-output module, a multi-scale window dividing module, an abnormal region estimation module and a boundary accurate module, wherein the input-output module is used for outputting multi-scale window dividing data;
the input and output module is used for inputting a magnetic leakage signal and outputting an abnormal target position region of a pipeline, and outputting the magnetic leakage signal to the multi-scale window dividing module;
the multi-scale window dividing module is used for completing the acquisition of a multi-scale candidate abnormal window and outputting the abnormal window to the abnormal region estimation module;
the abnormal region estimation module is used for estimating the position of an abnormal region to obtain an abnormal estimation set and outputting the set to the boundary accurate module;
the boundary accurate module is used for describing the boundary of each window in the abnormal estimation set in detail to obtain an abnormal recommendation area, and the abnormal recommendation areas are merged and then output to the input and output module.
On the other hand, the invention provides a method for recommending a multi-scale abnormal region of rapid pipeline magnetic leakage data, which is realized by the system for recommending the multi-scale abnormal region of the rapid pipeline magnetic leakage data, and comprises the following steps:
step 1: obtaining a magnetic leakage signal D of a section of pipeline, and carrying out multi-scale window division on the magnetic leakage signal D to divide the magnetic leakage signal D into N scale levels L 1 ,L 2 ,...L N And extracting abnormal edges of the N scale levels to obtain an abnormal window set W = { W = { (W) 1 ，W 2 ，...，W k ，…W N }; wherein,
a lower window set of the kth scale level is taken as b is the number of windows contained in the kth scale level;
step 2: carrying out abnormal region estimation on the abnormal window set obtained in the step 1 to obtain an abnormal estimation set W = { W ″) 1″ ，W 2″ ，...，W k″ ，…W N″ }；
Step 2.1: preprocessing the forms in the abnormal form set, wherein the preprocessing is to remove the forms with unclosed boundaries, and obtaining a processed abnormal form set W '= { W' = 1′ ，W 2′ ，...，W k′ ，…W N′ }；
Step 2.2: performing score estimation on the abnormal form set W'; as for the abnormal region, it is preferable that,a plurality of windows are overlapped to form a plurality of 'hui' shapes, and each window corresponds to a value S (W) for measuring the overlapping degree of the windows k′ ) Traversing the abnormal window set W', calculating the window overlapping degree value of each window, and equating the window overlapping degree value to the score of the abnormal window, wherein the formula is as follows:
wherein, W k′ Representing a current window, wherein m is the number of contour line windows contained in the current window;
respectively representing the number of frames in the kth window body and the number of frames outside the kth window body;
step 2.3: obtaining an abnormal region, selecting a window with the score larger than sigma as an abnormal window, wherein the score of the window is more than or equal to 0 and less than or equal to 1, judging whether parallel windows exist under the same scale level, if so, deleting all the parallel windows under the scale level to obtain an abnormal estimation set W '= { W' = 1″ ，W 2″ ，...，W k″ ，…W N″ }；
And 3, step 3: the boundary is accurate; according to the abnormal estimation set W' = { W obtained in the step 2 1″ ，W 2″ ，...，W k″ ，…W N″ H, mixing W k″ Performing area ratio of adjacent windows on all windows in the set, traversing the abnormal estimation set W', removing windows with the area ratio smaller than lambda, wherein lambda is more than or equal to 0 and less than or equal to 1, and selecting the outermost periphery window in the overlapped windows in the current set as an abnormal recommendation area;
the area ratio is formulated as follows:
wherein,
the area ratio of the h-1 window to the h window under the kth scale level is shown; the | × | represents the area of the window, namely the number of data points contained in the window;
Respectively representing the h-1 window and the h window under the kth scale level;
the specific steps of the step 1 are as follows:
step 1.1: for a section of pipeline leakage magnetic signal D, dividing N scale levels L between the minimum value and the maximum value of the leakage magnetic signal D 1 ,L 2 ,...L N Then, the value of the kth scale level is:
step 1.2: for a scale level k, the value L of the scale level is divided into k Slicing the current magnetic leakage signal D to obtain a binary matrix D k Namely:
wherein D i,j Data points of the ith row and the jth column in the pipeline magnetic leakage signal D are obtained;
step 1.3: for binary matrix D k And extracting abnormal edges.
Step 1.3.1: two orthogonal direction templates are established: horizontal template fx and vertical template fy, i.e.: fy = [ -1]；fx＝fy T And fx denotes the transpose of fy.
Step 1.3.2: using the horizontal template fx and the vertical template fy to pair the binary matrix D k Respectively filtering in two directions to obtain filtered binary matrix D k,x And D k,y (ii) a Binary matrix D k Has an edge matrix of E k ：
Step 1.3.3: obtaining abnormal edges, then regularizing the abnormal edges to form a rectangular window body to obtain a current scale level abnormal window body set W k ；
Step 1.4: repeating the steps 1.1 to 1.3 to obtain an abnormal window set W = { W } of all scale levels 1 ，W 2 ，...，W k ，…W N }。
Adopt the produced beneficial effect of above-mentioned technical scheme to lie in: the invention provides a system and a method for recommending a multi-scale abnormal region of quick pipeline magnetic leakage data. Compared with a common anomaly extraction algorithm, the method can not only discover the anomalies with larger size and obvious signals, but also discover smaller anomalies, and can provide sufficient anomaly candidate areas; compared with the common abnormal extraction algorithm completely based on the signal, the method has obvious rapidity and is particularly suitable for huge data sets of pipelines.
Drawings
Fig. 1 is a block diagram of a system for recommending a multi-scale abnormal region of flux leakage data of a fast pipeline according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for recommending a multi-scale abnormal region of flux leakage data of a fast pipeline according to an embodiment of the present invention;
fig. 3 is a schematic diagram of magnetic leakage data provided by an embodiment of the present invention;
fig. 4 is a schematic diagram of multi-scale slicing division provided by an embodiment of the present invention;
FIG. 5 is a schematic diagram of a multi-scale outlier edge provided in accordance with an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating multi-scale anomalous edge regularization according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a score estimation window provided in the embodiment of the present invention;
fig. 8 is a schematic diagram of a maximum inclusion relation combination window provided in the embodiment of the present invention;
FIG. 9 is a schematic diagram of a boundary precision window provided in an embodiment of the present invention;
fig. 10 is a schematic diagram of a maximum peripheral window provided in an embodiment of the present invention;
fig. 11 is a schematic diagram of a defect signal target area according to an embodiment of the present invention.
Detailed Description
The following detailed description of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention, but are not intended to limit the scope of the invention.
This embodiment is described below.
On one hand, the invention provides a system for recommending a multi-scale abnormal region of rapid pipeline magnetic flux leakage data, which comprises an input-output module, a multi-scale window dividing module, an abnormal region estimation module and a boundary accurate module, wherein the input-output module is used for outputting multi-scale window dividing data;
the input and output module is used for inputting a magnetic leakage signal and outputting an abnormal target position region of a pipeline, and outputting the magnetic leakage signal to the multi-scale window dividing module;
the multi-scale window dividing module is used for completing the acquisition of a multi-scale candidate abnormal window and outputting the abnormal window to the abnormal region estimation module;
the abnormal region estimation module is used for estimating the position of the abnormal region to obtain an abnormal estimation set and outputting the set to the boundary accurate module.
The boundary accurate module is used for describing the boundary of each window in the abnormal estimation set in detail to obtain an abnormal recommendation area, and the abnormal recommendation areas are merged and then output to the input and output module.
On the other hand, the invention provides a method for recommending a multi-scale abnormal region of rapid pipeline magnetic flux leakage data, which is implemented by the system for recommending the multi-scale abnormal region of the rapid pipeline magnetic flux leakage data, as shown in fig. 2, and comprises the following steps:
step 1: obtaining a magnetic leakage signal D of a section of pipeline, and carrying out multi-scale window division on the magnetic leakage signal D into N scale levels L 1 ,L 2 ,...L N And extracting abnormal edges of the N scale levels to obtain an abnormal window set W = { W = { (W) 1 ，W 2 ，...，W k ，…W N }. Wherein,
a window set under the k scale level is set, and b is the number of windows contained in the k scale level;
n =40 in this example;
step 1.1: for a section of pipeline leakage magnetic signal D, as shown in fig. 3, N scale levels L are divided between the minimum value and the maximum value of the leakage magnetic signal D 1 ,L 2 ,...L N Then the value of the kth scale level is:
in the embodiment, the pipeline magnetic flux leakage signal D is divided into 40 scale levels;
step 1.2: for a scale level k, the value L of the scale level is divided into k Slicing the current leakage signal D, as shown in FIG. 4, to obtain a binary matrix D k Namely:
wherein D i,j Data points of the ith row and the jth column in the pipeline magnetic leakage signal D are obtained;
step 1.3: for binary matrix D k And carrying out abnormal edge extraction.
Step 1.3.1: two orthogonal direction templates are established: horizontal template fx and vertical template fy, i.e.: fy = [ -1]；fx＝fy T And fx denotes the rotation of fyAnd (4) placing.
Step 1.3.2: using the horizontal template fx and the vertical template fy to pair the binary matrix D k Filtering in two directions respectively to obtain filtered binary matrix D k,x And D k,y (ii) a Binary matrix D k Has an edge matrix of E k ：
Step 1.3.3: obtaining abnormal edges, as shown in fig. 5, then regularizing the abnormal edges to form a rectangular window, as shown in fig. 6, obtaining an abnormal window set W of the current scale set k 。
Step 1.4: repeating the steps 1.1 to 1.3 to obtain an abnormal window set W = { W ] of all scale levels 1 ，W 2 ，...，W k ，…W N }。
And 2, step: performing abnormal region estimation on the abnormal window set obtained in the step 1 to obtain an abnormal estimation set W' = { W = 1″ ，W 2″ ，...，W k″ ，…W N″ }。
Step 2.1: preprocessing the forms in the abnormal form set, wherein the preprocessing is to remove the forms with the unclosed boundaries to obtain a processed abnormal form set W' = { W = 1′ ，W 2′ ，...，W k′ ，…W N′ }; we define that an exception frame exists with the following requirements: the outlier edge points can constitute an end-to-end connected closed area.
Step 2.2: performing score estimation on the abnormal window set W'; in practice, after the source data is divided into multiple scales and levels, for an abnormal area, multiple windows are overlapped together to form multiple ' Chinese character ' hui ' shapes. Thus, to characterize this characteristic, each window corresponds to a value S (W) that measures the degree of overlap of the windows k′ ) Traversing the abnormal window set W', calculating the window overlapping degree value of each window, and equating the window overlapping degree value as the score of the abnormal window, wherein the formula is as follows:
wherein, W k′ Representing a current window, wherein m is the number of contour line windows contained in the current window;
respectively representing the number of frames inside the kth window and the number of frames outside the kth window.
Step 2.3: obtaining abnormal regions, selecting the frames with the score larger than sigma as abnormal frames, wherein 0 is larger than or equal to sigma and smaller than or equal to 1 as shown in fig. 7, judging whether parallel frames exist under the same scale level, if so, deleting all the parallel frames under the scale level, as shown in fig. 8, and obtaining an abnormal estimation set W = { W ″, where 1″ ，W 2″ ，...，W k″ ，…W N″ }；
σ =0.7 in this example;
selecting a maximum inclusion relation combination window, and removing an interference window, namely: inside each frame, if any, the frames inside must belong to a full inclusion relationship.
And step 3: the boundary is accurate; as shown in fig. 9, the anomaly estimation set W ″ = { W ″, which is obtained in step 2 1″ ，W 2″ ，...，W k″ ，…W N″ Subjecting each of the sets to the above steps, for any one target region, covering multiple frames, in order to obtain an accurate boundary, we propose a spatial correlation ratio to measure the area ratio of adjacent frames, and apply W k″ All the windows in (1) perform area ratio of adjacent windows, traverse the abnormal estimation set W', and remove the windows with the area ratio smaller than lambda, wherein lambda is more than or equal to 0 and less than or equal to 1, and lambda =0.5 in the embodiment; selecting the outermost periphery window in the overlapped windows in the set after removing the window with the area ratio smaller than lambda as an abnormal recommendation area, as shown in fig. 10;
the area ratio is formulated as follows:
wherein,
the area ratio of the h-1 window to the h window under the kth scale level is obtained; the | × | represents the area of the window, namely the number of data points contained in the window;
Respectively representing the h-1 window and the h window under the kth scale level;
in this embodiment, the leakage signal defect is a leakage signal defect, which may generate three leakage signal region windows, where the middle window corresponds to the peak position and the two side windows correspond to the valley position, and the three windows are merged to obtain a final target position region, as shown in fig. 11;
finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications or substitutions do not depart from the spirit of the invention, which is defined by the claims.
Claims (1)
1. The utility model provides a regional recommendation system of quick pipeline magnetic leakage data multiscale anomaly which characterized in that: the system comprises an input and output module, a multi-scale window dividing module, an abnormal region estimation module and a boundary accurate module;
the input and output module is used for inputting magnetic leakage signals and outputting abnormal target position areas of the pipelines, and outputting the magnetic leakage signals to the multi-scale window dividing module;
the multi-scale window dividing module is used for completing the acquisition of a multi-scale candidate abnormal window and outputting the abnormal window to the abnormal region estimation module;
the abnormal region estimation module is used for estimating the position of an abnormal region to obtain an abnormal estimation set and outputting the set to the boundary accurate module;
the boundary accurate module is used for describing the boundary of each window in the abnormal estimation set in detail to obtain an abnormal recommendation area, and the abnormal recommendation areas are merged and then output to the input and output module;
the quick pipeline magnetic flux leakage data multi-scale abnormal region recommendation system is used for realizing a quick pipeline magnetic flux leakage data multi-scale abnormal region recommendation method and comprises the following steps:
step 1: obtaining a magnetic leakage signal D of a section of pipeline, and carrying out multi-scale window division on the magnetic leakage signal D to divide the magnetic leakage signal D into N scale levels L 1 ,L 2 ,...L N And extracting abnormal edges of the N scale levels to obtain an abnormal window set W = { W = { (W) 1 ，W 2 ，...，W k ，…W N }; wherein,
a window set under the k scale level is set, and b is the number of windows contained in the k scale level;
the specific steps of the step 1 are as follows:
step 1.1: for a section of pipeline leakage magnetic signal D, dividing N scale levels L between the minimum value and the maximum value of the leakage magnetic signal D 1 ,L 2 ,...L N Then, the value of the kth scale level is:
step 1.2: for a scale level k, the value L of the scale level is divided into k Slicing the current magnetic leakage signal D to obtain a binary matrix D k Namely:
wherein D i,j Data points of the ith row and the jth column in the pipeline magnetic leakage signal D are obtained;
step 1.3: for binary matrix D k Carrying out abnormal edge extraction;
step 1.3.1: two orthogonal direction templates are established: horizontal template fx and vertical template fy, i.e.: fy = [ -1]；fx＝fy T Fx denotes the transpose of fy;
step 1.3.2: using the horizontal template fx and the vertical template fy to pair the binary matrix D k Filtering in two directions respectively to obtain filtered binary matrix D k,x And D k,y (ii) a Binary matrix D k Is E k ：
Step 1.3.3: obtaining abnormal edges, then regularizing the abnormal edges to form a rectangular window body to obtain a current scale level abnormal window body set W k ；
Step 1.4: repeating the steps 1.1 to 1.3 to obtain an abnormal window set W = { W } of all scale levels 1 ，W 2 ，...，W k ，…W N }；
And 2, step: carrying out abnormal region estimation on the abnormal window set obtained in the step 1 to obtain an abnormal estimation set W' = { W = 1″ ，W 2″ ，...，W k″ ，…W N″ }；
Step 2.1: preprocessing the forms in the abnormal form set, wherein the preprocessing is to remove the forms with unclosed boundaries, and obtaining a processed abnormal form set W '= { W' = 1′ ，W 2′ ，...，W k′ ，…W N′ }；
Step 2.2: performing score estimation on the abnormal form set W'; for abnormal regions, a plurality of windows are overlapped to form a plurality of ' Chinese character ' hui ' shapes, and each window corresponds to a value S (W) for measuring the overlapping degree of the windows k′ ) Traversing the abnormal window set W', calculating the window overlapping degree value of each window, and equating the window overlapping degree value to the score of the abnormal window, wherein the formula is as follows:
wherein, W k′ Representing a current window, wherein m is the number of contour line windows contained in the current window;
respectively representing the number of window bodies in the kth window body and the number of window bodies outside the kth window body;
step 2.3: obtaining an abnormal region, selecting a window with the score larger than sigma as an abnormal window, wherein the score of the window is more than or equal to 0 and less than or equal to 1, judging whether parallel windows exist in the same scale level, if so, deleting all the parallel windows in the same scale level to obtain an abnormal estimation set W '= { W' = 1″ ，W 2″ ，...，W k″ ，…W N″ }；
And step 3: the boundary is accurate; according to the abnormal estimation set W' = { W obtained in the step 2 1″ ，W 2″ ，...，W k″ ，…W N″ H, mixing W k″ All the windows in the set are subjected to area ratio of adjacent windows, an abnormal estimation set W' is traversed, windows with the area ratio smaller than lambda are removed, lambda is more than or equal to 0 and less than or equal to 1, and the outermost peripheral window in the overlapped windows in the current set is selected as an abnormal recommendation area;
the area ratio is formulated as follows:
wherein,
is the h-1 window under the k scale levelThe area ratio of the body to the h window; the | | indicates the window area, namely the number of data points contained in the window;
Respectively representing the h-1 and h-1 frames at the k-th scale level. />
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910387892.8A CN110082424B (en) | 2019-05-10 | 2019-05-10 | Multi-scale abnormal region recommendation system and method for rapid pipeline magnetic flux leakage data |
| PCT/CN2019/087346 WO2020228044A1 (en) | 2019-05-10 | 2019-05-17 | Multiscale abnormal region rapid recommendation system and method for pipeline magnetic flux leakage data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910387892.8A CN110082424B (en) | 2019-05-10 | 2019-05-10 | Multi-scale abnormal region recommendation system and method for rapid pipeline magnetic flux leakage data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110082424A CN110082424A (en) | 2019-08-02 |
| CN110082424B true CN110082424B (en) | 2023-04-14 |
Family
ID=67419506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910387892.8A Active CN110082424B (en) | 2019-05-10 | 2019-05-10 | Multi-scale abnormal region recommendation system and method for rapid pipeline magnetic flux leakage data |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110082424B (en) |
| WO (1) | WO2020228044A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516589B (en) * | 2019-08-26 | 2023-06-02 | 东北大学 | Accurate boundary identification method for pipeline magnetic flux leakage data |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3654774B2 (en) * | 1998-08-13 | 2005-06-02 | 東京瓦斯株式会社 | Data display method for welding line position input in pipe inspection using leakage flux pig |
| GB0722534D0 (en) * | 2007-11-16 | 2007-12-27 | Advanced Eng Solutions Ltd | Pipeline condition detecting method and apparatus |
| CA2643219C (en) * | 2007-12-21 | 2017-08-22 | Knight, Inc. | System, method and program product to screen for longitudinal-seam anomalies |
| CN103343885B (en) * | 2013-06-20 | 2015-10-14 | 西南石油大学 | Pipeline Magnetic Flux Leakage Inspection online data compression method |
| CN104458895A (en) * | 2014-12-08 | 2015-03-25 | 清华大学 | Three-dimensional pipeline leakage flux imaging detection method and system |
| CN106645384B (en) * | 2016-09-23 | 2019-06-25 | 东北大学 | A kind of adaptive filter method of pipe leakage internal detector data |
| CN107024532B (en) * | 2017-04-12 | 2019-12-27 | 东北大学 | Method for extracting defect positions of magnetic leakage pipeline based on window features |
| CN109212018B (en) * | 2018-09-19 | 2022-06-03 | 东北大学 | Pipeline magnetic flux leakage data graded compression method based on compressed sensing |
| CN109058771B (en) * | 2018-10-09 | 2019-11-12 | 东北大学 | The pipeline method for detecting abnormality of Markov feature is generated and is spaced based on sample |
-
2019
- 2019-05-10 CN CN201910387892.8A patent/CN110082424B/en active Active
- 2019-05-17 WO PCT/CN2019/087346 patent/WO2020228044A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020228044A1 (en) | 2020-11-19 |
| CN110082424A (en) | 2019-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109783906B (en) | Intelligent analysis system and method for detecting magnetic flux leakage data in pipeline | |
| CN106950276B (en) | Pipeline defect depth inversion method based on convolutional neural network | |
| CN112329588A (en) | Pipeline fault detection method based on fast R-CNN | |
| CN109492708B (en) | LS-KNN-based pipeline magnetic flux leakage internal detection missing data interpolation method | |
| CN110555831B (en) | Deep learning-based drainage pipeline defect segmentation method | |
| CN113205051B (en) | Oil storage tank extraction method based on high spatial resolution remote sensing image | |
| CN111178392B (en) | Aero-engine hole detection image damage segmentation method based on deep neural network | |
| CN113030244B (en) | Inversion imaging method and system for transmission line tower corrosion defect magnetic flux leakage detection signal | |
| CN115823508A (en) | Air-ground integrated pipe network safety monitoring method and system | |
| CN113984880B (en) | Method and device for generating three-dimensional profile for pipeline metal loss defect | |
| CN115935241B (en) | Multi-parameter mutually-fused pipe cleaner real-time positioning method and device | |
| CN104899448A (en) | Adaptive compensation method for static localization scheme of ensemble Kalman filter | |
| CN110082424B (en) | Multi-scale abnormal region recommendation system and method for rapid pipeline magnetic flux leakage data | |
| Sun et al. | Research on fatigue crack growth detection of M (T) specimen based on image processing technology | |
| CN109632942B (en) | Inversion method of pipeline defect size based on ensemble learning | |
| CN106404893B (en) | A kind of axial direction pipeline magnetic flux leakage defect automatic signal detection method | |
| CN107024532B (en) | Method for extracting defect positions of magnetic leakage pipeline based on window features | |
| CN113111923A (en) | Water supply network leakage detection and positioning method based on one-dimensional migration learning convolutional neural network integrated model | |
| CN115063337A (en) | Intelligent maintenance decision-making method and device for buried pipeline | |
| CN112287895A (en) | Model construction method, recognition method and system for river drain outlet detection | |
| CN112347903B (en) | Multi-component pipeline identification method based on heterogeneous field signals | |
| CN114596291B (en) | Road defect detection method based on deep learning and self-attention mechanism | |
| CN115082650A (en) | Implementation method of automatic pipeline defect labeling tool based on convolutional neural network | |
| Jiang | Study of underground oil-gas pipeline corrosion pits estimation based on MFL inspection method | |
| Yasuno et al. | One-class steel detector using patch GAN discriminator for visualising anomalous feature map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |